Agent skill

Building Detection Rules With Sigma

by mukul975 in mukul975/Anthropic-Cybersecurity-Skills

Builds vendor-agnostic detection rules using the Sigma rule format for threat detection across SIEM platforms including Splunk, Elastic, and Microsoft Sentinel.

Apache-2.0Auto-check passedSecurity

Install Building Detection Rules With Sigma

skills CLI
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill building-detection-rules-with-sigma -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills building-detection-rules-with-sigma --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/building-detection-rules-with-sigma .claude/skills/building-detection-rules-with-sigma && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
building-detection-rules-with-sigma
GitHub stars
34k
Token cost
~2.7k tokens
SKILL.md length
500 words
Files
4 (incl. scripts, references)
Skills in repo
644
Repo updated
First seen
Licence
Apache-2.0

At a glance

Builds vendor-agnostic detection rules using the Sigma rule format for threat detection across SIEM platforms including Splunk, Elastic, and Microsoft Sentinel.

  • Works in 7 steps: Define Detection Logic from Threat… → Validate Sigma Rule Syntax → Convert to Target SIEM Query → …
  • Creating portable detection logic from threat intelligence
  • SKILL.md covers When to Use, Prerequisites, Workflow and Key Concepts, plus 3 more sections
  • Runs Python scripts from its folder; calls pip and git; reaches github.com and attack.mitre.org

What it does

Building Detection Rules With Sigma is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Builds vendor-agnostic detection rules using the Sigma rule format for threat detection across SIEM platforms including Splunk, Elastic, and Microsoft Sentinel. Use when creating portable detection logic from threat intelligence, mapping rules to MITRE ATT&CK techniques, or converting community Sigma rules into platform-specific queries using sigmac or pySigma backends.

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `references/api-reference.md` and `scripts/agent.py`).

It sits in Security, covering Security operations and OSINT. It works with Splunk and Microsoft Sentinel. The repository describes itself as: 817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io…. The licence is Apache-2.0.

When your agent uses it

  • Creating portable detection logic from threat intelligence
  • Mapping rules to MITRE ATT&CK techniques
  • Converting community Sigma rules into platform-specific queries using sigmac
  • PySigma backends

Example prompts

  • “Use the building-detection-rules-with-sigma skill to build vendor-agnostic detection rules using the Sigma rule format for threat detection across…”
  • “/building-detection-rules-with-sigma”

Requirements

  • Python 3

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Define Detection Logic from Threat Intelligence
  2. Validate Sigma Rule Syntax
  3. Convert to Target SIEM Query
  4. Map to MITRE ATT&CK and Add Coverage Metadata
  5. Test Rule Against Sample Data
  6. Deploy to Production SIEM
  7. Version Control and CI/CD Integration

What it can do on your machine

Read from SKILL.md and the folder at commit 54a7988. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • pip
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com
    • attack.mitre.org

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Building Detection Rules With Sigma loads about 2.7k tokens when it runs, and up to ~3.2k if it reads all its reference files. Until then it costs about 102 tokens; SKILL.md has 500 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~102
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from mukul975/Anthropic-Cybersecurity-Skills at commit 54a7988, republished under its Apache-2.0 licence (© mukul975). 500 words, ~2,658 tokens.

Download SKILL.mdSave it as .claude/skills/building-detection-rules-with-sigma/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
building-detection-rules-with-sigma
description
Builds vendor-agnostic detection rules using the Sigma rule format for threat detection across SIEM platforms including Splunk, Elastic, and Microsoft Sentinel. Use when creating portable detection logic from threat intelligence, mapping rules to MITRE ATT&CK techniques, or converting community Sigma rules into platform-specific queries using sigmac or pySigma backends.
domain
cybersecurity
subdomain
soc-operations
tags
soc, sigma, detection-rules, siem, mitre-attack, splunk, elastic, sentinel
version
1.0
author
mahipal
license
Apache-2.0
d3fend_techniques
Execution Isolation, Process Termination, Hardware-based Process Isolation, Web Session Access Mediation, Process Suspension
nist_csf
DE.CM-01, DE.AE-02, RS.MA-01, DE.AE-06
mitre_attack
T1059.001, T1003.001, T1055, T1053.005, T1547.001

Building Detection Rules with Sigma

When to Use

Use this skill when:

  • SOC engineers need to create detection rules portable across multiple SIEM platforms
  • Threat intelligence reports describe TTPs requiring new detection coverage
  • Existing vendor-specific rules need standardization into a shareable format
  • The team adopts Sigma as a detection-as-code standard in CI/CD pipelines

Do not use for real-time streaming detection (Sigma is for batch/scheduled searches) or when the target SIEM has native detection features that Sigma cannot express (e.g., Splunk RBA risk scoring).

Prerequisites

  • Python 3.8+ with pySigma and appropriate backend (pySigma-backend-splunk, pySigma-backend-elasticsearch, pySigma-backend-microsoft365defender)
  • Sigma rule repository cloned: git clone https://github.com/SigmaHQ/sigma.git
  • MITRE ATT&CK framework knowledge for technique mapping
  • Understanding of target SIEM log source field mappings

Workflow

Step 1: Define Detection Logic from Threat Intelligence

Start with a threat report or ATT&CK technique. Example: detecting Mimikatz credential dumping (T1003.001 — LSASS Memory):

yaml
title: Mimikatz Credential Dumping via LSASS Access
id: 0d894093-71bc-43c3-8d63-bf520e73a7c5
status: stable
level: high
description: Detects process accessing lsass.exe memory, indicative of credential dumping tools like Mimikatz
references:
    - https://attack.mitre.org/techniques/T1003/001/
    - https://github.com/gentilkiwi/mimikatz
author: mahipal
date: 2024/03/15
modified: 2024/03/15
tags:
    - attack.credential_access
    - attack.t1003.001
logsource:
    category: process_access
    product: windows
detection:
    selection:
        TargetImage|endswith: '\lsass.exe'
        GrantedAccess|contains:
            - '0x1010'
            - '0x1038'
            - '0x1fffff'
            - '0x40'
    filter_main_svchost:
        SourceImage|endswith: '\svchost.exe'
    filter_main_csrss:
        SourceImage|endswith: '\csrss.exe'
    filter_main_wininit:
        SourceImage|endswith: '\wininit.exe'
    condition: selection and not 1 of filter_main_*
falsepositives:
    - Legitimate security tools accessing LSASS
    - Windows Defender scanning
    - CrowdStrike Falcon sensor
Step 2: Validate Sigma Rule Syntax

Use sigma check to validate the rule:

bash
# Install pySigma and validators
pip install pySigma pySigma-validators-sigmaHQ

# Validate rule
sigma check rule.yml

Alternatively, validate with Python:

python
from sigma.rule import SigmaRule
from sigma.validators.core import SigmaValidator

rule = SigmaRule.from_yaml(open("rule.yml").read())
validator = SigmaValidator()
issues = validator.validate_rule(rule)
for issue in issues:
    print(f"{issue.severity}: {issue.message}")
Step 3: Convert to Target SIEM Query

Convert to Splunk SPL:

python
from sigma.rule import SigmaRule
from sigma.backends.splunk import SplunkBackend
from sigma.pipelines.splunk import splunk_windows_pipeline

pipeline = splunk_windows_pipeline()
backend = SplunkBackend(pipeline)

rule = SigmaRule.from_yaml(open("rule.yml").read())
splunk_query = backend.convert_rule(rule)
print(splunk_query[0])

Output:

spl
TargetImage="*\\lsass.exe" (GrantedAccess="*0x1010*" OR GrantedAccess="*0x1038*"
OR GrantedAccess="*0x1fffff*" OR GrantedAccess="*0x40*")
NOT (SourceImage="*\\svchost.exe") NOT (SourceImage="*\\csrss.exe")
NOT (SourceImage="*\\wininit.exe")

Convert to Elastic Query (Lucene):

python
from sigma.backends.elasticsearch import LuceneBackend
from sigma.pipelines.elasticsearch import ecs_windows_pipeline

pipeline = ecs_windows_pipeline()
backend = LuceneBackend(pipeline)
elastic_query = backend.convert_rule(rule)
print(elastic_query[0])

Convert to Microsoft Sentinel KQL:

python
from sigma.backends.microsoft365defender import Microsoft365DefenderBackend

backend = Microsoft365DefenderBackend()
kql_query = backend.convert_rule(rule)
print(kql_query[0])
Step 4: Map to MITRE ATT&CK and Add Coverage Metadata

Tag every rule with ATT&CK technique IDs in the tags field:

yaml
tags:
    - attack.credential_access        # Tactic
    - attack.t1003.001                # Sub-technique
    - attack.t1003                    # Parent technique

Track detection coverage using the ATT&CK Navigator:

python
import json

# Generate ATT&CK Navigator layer from Sigma rules
layer = {
    "name": "SOC Detection Coverage",
    "versions": {"attack": "14", "navigator": "4.9", "layer": "4.5"},
    "domain": "enterprise-attack",
    "techniques": []
}

# Parse Sigma rules directory for technique tags
import os
from sigma.rule import SigmaRule

for root, dirs, files in os.walk("sigma/rules/windows/"):
    for f in files:
        if f.endswith(".yml"):
            rule = SigmaRule.from_yaml(open(os.path.join(root, f)).read())
            for tag in rule.tags:
                if str(tag).startswith("attack.t"):
                    technique_id = str(tag).replace("attack.", "").upper()
                    layer["techniques"].append({
                        "techniqueID": technique_id,
                        "color": "#31a354",
                        "score": 1
                    })

with open("coverage_layer.json", "w") as f:
    json.dump(layer, f, indent=2)
Step 5: Test Rule Against Sample Data

Create test data and validate the rule catches the expected events:

bash
# Use sigma test framework
sigma test rule.yml --target splunk --pipeline splunk_windows

# Or manually test in Splunk with sample data
# Upload Sysmon process_access log with known Mimikatz signature

Validate false positive rate by running against 7 days of production data in a non-alerting saved search.

Step 6: Deploy to Production SIEM

Deploy the converted query as a scheduled search or correlation rule:

Splunk ES Correlation Search:

spl
| tstats summariesonly=true count from datamodel=Endpoint.Processes
  where Processes.process_name="*\\lsass.exe"
  by Processes.src, Processes.user, Processes.process_name, Processes.parent_process_name
| `drop_dm_object_name(Processes)`
| where count > 0

Elastic Security Rule (TOML format):

toml
[rule]
name = "LSASS Memory Access - Credential Dumping"
description = "Detects suspicious access to LSASS process memory"
risk_score = 73
severity = "high"
type = "eql"
query = '''
process where event.action == "access" and
  process.name == "lsass.exe" and
  not process.executable : ("*\\svchost.exe", "*\\csrss.exe")
'''

[rule.threat]
framework = "MITRE ATT&CK"
[[rule.threat.technique]]
id = "T1003"
name = "OS Credential Dumping"
Step 7: Version Control and CI/CD Integration

Store rules in Git with automated testing:

yaml
# .github/workflows/sigma-ci.yml
name: Sigma Rule CI
on: [push, pull_request]
jobs:
  validate:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-python@v5
        with:
          python-version: '3.11'
      - run: pip install pySigma pySigma-validators-sigmaHQ
      - run: sigma check rules/
      - run: sigma convert -t splunk -p splunk_windows rules/ > /dev/null
Show full SKILL.md (217 more words)Show less

Key Concepts

TermDefinition
SigmaVendor-agnostic detection rule format (YAML-based) that compiles to SIEM-specific queries via backends
pySigmaPython library replacing legacy sigmac for rule conversion, validation, and pipeline processing
BackendpySigma plugin that translates Sigma detection logic into a target platform query language (SPL, KQL, Lucene)
PipelineField mapping configuration that translates generic Sigma field names to SIEM-specific field names
LogsourceSigma rule section defining the category (process_creation, network_connection) and product (windows, linux) of the target data
Detection-as-CodePractice of managing detection rules in version control with CI/CD testing and automated deployment

Tools & Systems

  • SigmaHQ: Official Sigma rule repository with 3,000+ community-maintained detection rules on GitHub
  • pySigma: Python-based Sigma rule processing framework with modular backends and pipelines
  • ATT&CK Navigator: MITRE tool for visualizing detection coverage mapped to ATT&CK techniques
  • Uncoder.IO: Web-based Sigma rule converter supporting 30+ SIEM platforms for quick translation

Common Scenarios

  • New CVE Detection: Write Sigma rule for exploitation indicators (e.g., Log4Shell JNDI lookup patterns in web logs)
  • Hunting Rule Promotion: Convert ad-hoc Splunk hunting query into Sigma rule for ongoing automated detection
  • Multi-SIEM Migration: Converting 500+ Splunk correlation searches to Sigma for migration to Elastic Security
  • Purple Team Output: Convert red team findings into Sigma rules for immediate defensive coverage
  • Threat Intel Operationalization: Transform IOC-based threat reports into behavioral Sigma rules

Output Format

SIGMA RULE DEPLOYMENT REPORT
━━━━━━━━━━━━━━━━━━━━━━━━━━━
Rule ID:      0d894093-71bc-43c3-8d63-bf520e73a7c5
Title:        Mimikatz Credential Dumping via LSASS Access
ATT&CK:       T1003.001 - LSASS Memory
Severity:     High
Status:       Deployed to Production

Conversions:
  Splunk SPL:    PASS — Saved search "sigma_lsass_access" created
  Elastic EQL:   PASS — Detection rule ID elastic-0d894093 enabled
  Sentinel KQL:  PASS — Analytics rule deployed via ARM template

Testing:
  True Positives:    4/4 test cases matched
  False Positives:   2 in 7-day backtest (svchost edge case — filter added)
  Performance:       Avg execution 3.2s on 50M events/day

© mukul975, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts, references) in skills/building-detection-rules-with-sigma of mukul975/Anthropic-Cybersecurity-Skills.

  • SKILL.md
  • LICENSE
  • references/api-reference.md
  • scripts/agent.py

Open the folder on GitHubat commit 54a7988

Compare with similar skills

Building Detection Rules With Sigma next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Building Detection Rules With Sigma compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Building Detection Rules With Sigma this skillmukul975/Anthropic-Cybersecurity-Skills34k—~2.7kAutomated safety check: PassApache-2.0
Siem Loggingancoleman/ai-design-components525—~3.4kAutomated safety check: PassMIT
Threat Intel CampaignSCStelz/security-investigator249—~6.9kAutomated safety check: PassMIT
Unified Secops Platformvinayaklatthe/microsoft-security-skills175—~2.1kAutomated safety check: PassMIT
Siem Detectionbriiirussell/cybersecurity-skills413—~2.6kAutomated safety check: NotesMIT
Hunting Threatstrilwu/secskills157—~3.5kAutomated safety check: PassMIT

Similar skills

  • Siem Logging

    ancoleman/ai-design-components

    Configure security information and event management (SIEM) systems for threat detection, log aggregation, and compliance.

    525 GitHub stars~3.4k tokensUpdated 10 mo ago
    SecurityAuto-check passed
  • Threat Intel Campaign

    SCStelz/security-investigator

    Turn a published threat-intelligence article into a tested threat-hunting campaign.

    249 GitHub stars~6.9k tokensUpdated 2 days ago
    SecurityAuto-check passed
  • Unified Secops Platform

    vinayaklatthe/microsoft-security-skills

    Guidance for the Microsoft unified security operations platform that brings Microsoft Sentinel, Microsoft Defender XDR, Security Copilot, Threat Intelligence, and Microsoft Security Exposure…

    175 GitHub stars~2.1k tokensUpdated 3 mo ago
    SecurityAuto-check passed
  • Siem Detection

    briiirussell/cybersecurity-skills

    Engineer and audit SIEM detection rules — log source coverage, Sigma / KQL / SPL / Elastic query authoring, MITRE ATT&CK mapping, false-positive tuning, and detection-as-code workflows.

    413 GitHub stars~2.6k tokensUpdated 4 mo ago
    SecurityAuto-check: notes
  • Hunting Threats

    trilwu/secskills

    Run hypothesis-driven threat hunts across endpoint, network, cloud, and identity telemetry using stack counting, outlier analysis, and ATT&CK-based hypotheses, with SIEM query patterns for Splunk…

    157 GitHub stars~3.5k tokensUpdated 1 mo ago
    SecurityAuto-check passed
  • Enrich Ioc

    dandye/ai-runbooks

    Enrich an IOC (IP, domain, hash, URL) with threat intelligence.

    127 GitHub stars~702 tokensUpdated 1 mo ago
    SecurityAuto-check passed

More from mukul975/Anthropic-Cybersecurity-Skills

All 644 skills in this repo
  • Campaign Attribution Evidence Analysis

    mukul975/Anthropic-Cybersecurity-Skills

    Weighs infrastructure, TTP, malware code and timing evidence with the Diamond Model and competing hypotheses to reach a confidence-rated attribution.

    34k GitHub stars~2.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Go Malware Analysis in Ghidra

    mukul975/Anthropic-Cybersecurity-Skills

    Walks through reverse engineering Go-compiled malware in Ghidra: parsing buildinfo and pclntab, recovering stripped function names and extracting dependencies.

    34k GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check passed
  • LNK and Jump List Forensics

    mukul975/Anthropic-Cybersecurity-Skills

    Guides forensic analysis of Windows LNK shortcut files and Jump Lists with LECmd, JLECmd and manual parsing to show file access and program execution.

    34k GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Malware Persistence Analysis with Autoruns

    mukul975/Anthropic-Cybersecurity-Skills

    Hunts Windows malware persistence with Sysinternals Autoruns, covering run keys, services, scheduled tasks and drivers, with baseline comparison.

    34k GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed
  • NTFS MFT Deleted File Recovery

    mukul975/Anthropic-Cybersecurity-Skills

    Guides a Windows forensic examination of the NTFS Master File Table to recover deleted-file evidence, build timelines and spot timestomping.

    34k GitHub stars~2.7k tokensUpdated 1 mo ago
    Auto-check passed
  • Network Covert Channel Analysis

    mukul975/Anthropic-Cybersecurity-Skills

    Detects DNS tunneling, ICMP exfiltration and HTTP-based covert channels in packet captures and DNS logs when hunting for hidden command-and-control traffic.

    34k GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Building Detection Rules With Sigma

What does Building Detection Rules With Sigma do?

Builds vendor-agnostic detection rules using the Sigma rule format for threat detection across SIEM platforms including Splunk, Elastic, and Microsoft Sentinel. Building Detection Rules With Sigma is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. Builds vendor-agnostic detection rules using the Sigma rule format for threat detection across SIEM platforms including Splunk, Elastic, and Microsoft Sentinel.

When should I use Building Detection Rules With Sigma?

Building Detection Rules With Sigma fits situations like: creating portable detection logic from threat intelligence; mapping rules to MITRE ATT&CK techniques; converting community Sigma rules into platform-specific queries using sigmac; pySigma backends.

How do I install Building Detection Rules With Sigma in Claude Code?

Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill building-detection-rules-with-sigma -a claude-code`. Or copy the skill folder (skills/building-detection-rules-with-sigma in mukul975/Anthropic-Cybersecurity-Skills) into .claude/skills/building-detection-rules-with-sigma in your project. Claude Code loads it when a task matches its description.

How do I install Building Detection Rules With Sigma in Codex?

Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill building-detection-rules-with-sigma -a codex`. Or copy the skill folder (skills/building-detection-rules-with-sigma in mukul975/Anthropic-Cybersecurity-Skills) into .agents/skills/building-detection-rules-with-sigma in your project. Codex loads it when a task matches its description.

Can I use Building Detection Rules With Sigma in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill building-detection-rules-with-sigma -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/building-detection-rules-with-sigma, .gemini/skills/building-detection-rules-with-sigma, .github/skills/building-detection-rules-with-sigma and .opencode/skills/building-detection-rules-with-sigma in your project.

What does Building Detection Rules With Sigma need to run?

Going by SKILL.md and its folder, Building Detection Rules With Sigma needs Python for the scripts in its folder and the command-line tools its instructions call (pip and git). Our summary lists: Python 3.

Does Building Detection Rules With Sigma access the network?

SKILL.md names 2 domains. In commands or code: github.com and attack.mitre.org; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Building Detection Rules With Sigma safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Building Detection Rules With Sigma use?

Building Detection Rules With Sigma is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Building Detection Rules With Sigma use?

About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 532 tokens, read only when the agent opens those files.

What are the alternatives to Building Detection Rules With Sigma?

Skills that share tags, products or a category with Building Detection Rules With Sigma: Siem Logging (ancoleman/ai-design-components, 525 stars), Threat Intel Campaign (SCStelz/security-investigator, 249 stars), Unified Secops Platform (vinayaklatthe/microsoft-security-skills, 175 stars) and Siem Detection (briiirussell/cybersecurity-skills, 413 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Building Detection Rules With Sigma?

mukul975 (a GitHub user) maintains it in mukul975/Anthropic-Cybersecurity-Skills, which has 34,116 GitHub stars. The repository holds 644 skills in this directory. The repository was last updated on August 31, 2026.

Source: mukul975/Anthropic-Cybersecurity-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.